Boosting Single Positive Multi-label Classification with Generalized Robust Loss

TL;DR

This paper introduces a generalized loss framework for single positive multi-label learning that effectively balances false positives and negatives, significantly improving performance over existing methods.

Contribution

It proposes a novel generalized loss framework based on expected risk minimization, enabling soft pseudo labels and flexible handling of label imbalance in SPML.

Findings

Significant performance improvements on four benchmarks

Outperforms most state-of-the-art SPML methods

Effectively balances false positives and negatives

Abstract

Multi-label learning (MLL) requires comprehensive multi-semantic annotations that is hard to fully obtain, thus often resulting in missing labels scenarios. In this paper, we investigate Single Positive Multi-label Learning (SPML), where each image is associated with merely one positive label. Existing SPML methods only focus on designing losses using mechanisms such as hard pseudo-labeling and robust losses, mostly leading to unacceptable false negatives. To address this issue, we first propose a generalized loss framework based on expected risk minimization to provide soft pseudo labels, and point out that the former losses can be seamlessly converted into our framework. In particular, we design a novel robust loss based on our framework, which enjoys flexible coordination between false positives and false negatives, and can additionally deal with the imbalance between positive and negative samples. Extensive experiments show that our approach can significantly improve SPML performance and outperform the vast majority of state-of-the-art methods on all the four benchmarks.